cloudyu-nemo-dpo-v18

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v18_v1

model_name: cloudyu-nemo-dpo-v18_v1

model_group: cloudyu/Nemo-DPO-V18

status: inactive

timestamp: 2024-12-07T01:33:45+00:00

num_battles: 18196

num_wins: 9391

celo_rating: 1274.26

family_friendly_score: 0.5494

family_friendly_standard_error: 0.007036471274722863

submission_type: basic

model_repo: cloudyu/Nemo-DPO-V18

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6199381553047061, 'latency_mean': 1.613002827167511, 'latency_p50': 1.6240174770355225, 'latency_p90': 1.7730692386627198}, {'batch_size': 3, 'throughput': 1.1502808018206194, 'latency_mean': 2.6026321446895597, 'latency_p50': 2.5876764059066772, 'latency_p90': 2.88356294631958}, {'batch_size': 5, 'throughput': 1.3778746773306174, 'latency_mean': 3.604825415611267, 'latency_p50': 3.6337032318115234, 'latency_p90': 4.040848803520203}, {'batch_size': 6, 'throughput': 1.470223329911158, 'latency_mean': 4.065306103229522, 'latency_p50': 4.060610294342041, 'latency_p90': 4.631509160995483}, {'batch_size': 8, 'throughput': 1.542327166567202, 'latency_mean': 5.161922821998596, 'latency_p50': 5.174460411071777, 'latency_p90': 5.804859590530396}, {'batch_size': 10, 'throughput': 1.5819801666427042, 'latency_mean': 6.271381285190582, 'latency_p50': 6.267035722732544, 'latency_p90': 7.079959440231323}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v18_v1

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-V18

model_size: 13B

ranking_group: single

throughput_3p7s: 1.41

us_pacific_date: 2024-12-06

win_ratio: 0.5161024400967246

generation_params: {'temperature': 1.25, 'top_p': 0.99, 'min_p': 0.01, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name cloudyu-nemo-dpo-v18-v1-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v18-v1-mkmlizer to finish
cloudyu-nemo-dpo-v18-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v18-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v18-v1-mkmlizer: Downloaded to shared memory in 55.694s
cloudyu-nemo-dpo-v18-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsse_hjjz, device:0
cloudyu-nemo-dpo-v18-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v18-v1-mkmlizer: quantized model in 35.830s
cloudyu-nemo-dpo-v18-v1-mkmlizer: Processed model cloudyu/Nemo-DPO-V18 in 91.525s
cloudyu-nemo-dpo-v18-v1-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v18-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v18-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v18-v1
cloudyu-nemo-dpo-v18-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v18-v1/config.json
cloudyu-nemo-dpo-v18-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v18-v1/special_tokens_map.json
cloudyu-nemo-dpo-v18-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v18-v1/tokenizer_config.json
cloudyu-nemo-dpo-v18-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v18-v1/tokenizer.json
cloudyu-nemo-dpo-v18-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v18-v1/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v18-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.12it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 47.22it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.25it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.04it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.21it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 46.16it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.89it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.41it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.85it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.82it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 35.65it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.49it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 39.19it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:07, 39.38it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 44.61it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 44.40it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 36.27it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 41.14it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 40.60it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:06, 39.78it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 47.42it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 44.47it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 43.53it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 34.60it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.23it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.26it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 41.10it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 40.99it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:04, 41.82it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:03, 47.62it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 44.88it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 43.29it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 48.37it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 45.82it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 44.07it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 48.79it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 46.44it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 36.21it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 36.01it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 35.55it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 39.53it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:03, 39.62it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 39.31it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 44.14it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 43.89it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 43.63it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 44.75it/s]
Loading 0:  76%|███████▌  | 275/363 [00:06<00:02, 37.55it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 45.79it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 43.70it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 42.55it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 48.58it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:19,  2.81it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:13,  3.71it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.75it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:05,  7.36it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:03,  9.03it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.45it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:01, 16.46it/s]
Loading 0:  96%|█████████▌| 348/363 [00:14<00:00, 18.36it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.21it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 28.58it/s]
                                                            
Job cloudyu-nemo-dpo-v18-v1-mkmlizer completed after 116.75s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v18-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.31s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v18-v1
Waiting for inference service cloudyu-nemo-dpo-v18-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-nemo-dpo-v18-v1 ready after 181.71447801589966s
Pipeline stage MKMLDeployer completed in 182.86s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5810883045196533s
Received healthy response to inference request in 1.7200233936309814s
Received healthy response to inference request in 1.6968441009521484s
Received healthy response to inference request in 1.9501349925994873s
Received healthy response to inference request in 1.697169303894043s
5 requests
0 failed requests
5th percentile: 1.6969091415405273
10th percentile: 1.6969741821289062
20th percentile: 1.697104263305664
30th percentile: 1.7017401218414308
40th percentile: 1.710881757736206
50th percentile: 1.7200233936309814
60th percentile: 1.8120680332183838
70th percentile: 1.904112672805786
80th percentile: 2.0763256549835205
90th percentile: 2.328706979751587
95th percentile: 2.45489764213562
99th percentile: 2.5558501720428466
mean time: 1.9290520191192626
Pipeline stage StressChecker completed in 10.86s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.23s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.08s
Shutdown handler de-registered
cloudyu-nemo-dpo-v18_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-nemo-dpo-v18-v1-profiler
Waiting for inference service cloudyu-nemo-dpo-v18-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2754.71s
Shutdown handler de-registered
cloudyu-nemo-dpo-v18_v1 status is now inactive due to auto deactivation removed underperforming models